tdnathmlenthusiast's picture
End of training
68a0495 verified
|
raw
history blame
1.97 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_finetuned_German_dataset
    results: []

speecht5_finetuned_German_dataset

This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4241

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 125
  • training_steps: 5000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5004 8.4567 500 0.4634
0.475 16.9133 1000 0.4414
0.4581 25.3700 1500 0.4318
0.4439 33.8266 2000 0.4268
0.4446 42.2833 2500 0.4266
0.4377 50.7400 3000 0.4288
0.4343 59.1966 3500 0.4296
0.4372 67.6533 4000 0.4282
0.4405 76.1099 4500 0.4282
0.4218 84.5666 5000 0.4241

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.5.0+cu121
  • Datasets 3.0.2
  • Tokenizers 0.19.1